2 * Copyright (c) 2002-2004 Tim J. Robbins
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 * PRC National Standard GB 18030-2000 encoding of Chinese text.
29 * See gb18030(5) for details.
32 #include <sys/param.h>
33 __FBSDID("$FreeBSD$");
42 static size_t _GB18030_mbrtowc(wchar_t * __restrict, const char * __restrict,
43 size_t, mbstate_t * __restrict);
44 static int _GB18030_mbsinit(const mbstate_t *);
45 static size_t _GB18030_wcrtomb(char * __restrict, wchar_t,
46 mbstate_t * __restrict);
54 _GB18030_init(_RuneLocale *rl)
57 __mbrtowc = _GB18030_mbrtowc;
58 __wcrtomb = _GB18030_wcrtomb;
59 __mbsinit = _GB18030_mbsinit;
60 _CurrentRuneLocale = rl;
67 _GB18030_mbsinit(const mbstate_t *ps)
70 return (ps == NULL || ((const _GB18030State *)ps)->count == 0);
74 _GB18030_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s,
75 size_t n, mbstate_t * __restrict ps)
82 gs = (_GB18030State *)ps;
84 if (gs->count < 0 || gs->count > sizeof(gs->bytes)) {
95 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count);
96 memcpy(gs->bytes + gs->count, s, ncopy);
99 s = (char *)gs->bytes;
103 /* Incomplete multibyte sequence */
107 * Single byte: [00-7f]
108 * Two byte: [81-fe][40-7e,80-fe]
109 * Four byte: [81-fe][30-39][81-fe][30-39]
111 ch = (unsigned char)*s++;
115 } else if (ch >= 0x81 && ch <= 0xfe) {
119 ch = (unsigned char)*s++;
120 if ((ch >= 0x40 && ch <= 0x7e) || (ch >= 0x80 && ch <= 0xfe)) {
121 wch = (wch << 8) | ch;
123 } else if (ch >= 0x30 && ch <= 0x39) {
125 * Strip high bit off the wide character we will
126 * eventually output so that it is positive when
127 * cast to wint_t on 32-bit twos-complement machines.
129 wch = ((wch & 0x7f) << 8) | ch;
132 ch = (unsigned char)*s++;
133 if (ch < 0x81 || ch > 0xfe)
135 wch = (wch << 8) | ch;
138 ch = (unsigned char)*s++;
139 if (ch < 0x30 || ch > 0x39)
141 wch = (wch << 8) | ch;
151 return (wch == L'\0' ? 0 : len - ocount);
158 _GB18030_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
164 gs = (_GB18030State *)ps;
166 if (gs->count != 0) {
172 /* Reset to initial shift state (no-op) */
174 if ((wc & ~0x7fffffff) != 0)
176 if (wc & 0x7f000000) {
177 /* Replace high bit that mbrtowc() removed. */
179 c = (wc >> 24) & 0xff;
180 if (c < 0x81 || c > 0xfe)
183 c = (wc >> 16) & 0xff;
184 if (c < 0x30 || c > 0x39)
187 c = (wc >> 8) & 0xff;
188 if (c < 0x81 || c > 0xfe)
192 if (c < 0x30 || c > 0x39)
196 } else if (wc & 0x00ff0000)
198 else if (wc & 0x0000ff00) {
199 c = (wc >> 8) & 0xff;
200 if (c < 0x81 || c > 0xfe)
204 if (c < 0x40 || c == 0x7f || c == 0xff)
208 } else if (wc <= 0x7f) {